• Publications
  • Influence
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
TLDR
CURL extracts high-level features from raw pixels using contrastive learning and performs off-policy control on top of the extracted features and is the first image-based algorithm to nearly match the sample-efficiency of methods that use state-based features.
Reinforcement Learning with Augmented Data
TLDR
It is shown that augmentations such as random translate, crop, color jitter, patch cutout, random convolutions, and amplitude scale can enable simple RL algorithms to outperform complex state-of-the-art methods across common benchmarks.
Decision Transformer: Reinforcement Learning via Sequence Modeling
TLDR
Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art model-free offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.
Decoupling Representation Learning from Reinforcement Learning
TLDR
A new unsupervised learning task, called Augmented Temporal Contrast (ATC), which trains a convolutional encoder to associate pairs of observations separated by a short time difference, under image augmentations and using a contrastive loss.
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
TLDR
SUNRISE is a simple unified ensemble method, which is compatible with various off-policy RL algorithms and significantly improves the performance of existing off-Policy RL algorithms, such as Soft Actor-Critic and Rainbow DQN, for both continuous and discrete control tasks on both low-dimensional and high-dimensional environments.
A Framework for Efficient Robotic Manipulation
TLDR
It is shown that, given only 10 demonstrations, a single robotic arm can learn sparse-reward manipulation policies from pixels, such as reaching, picking, moving, pulling a large object, flipping a switch, and opening a drawer in just 15-50 minutes of real-world training time.
Sparse Graphical Memory for Robust Planning
TLDR
SGM is introduced, a new data structure that stores states and feasible transitions in a sparse memory that significantly outperforms current state of the art methods on long horizon, sparse-reward visual navigation tasks.
Hierarchical Few-Shot Imitation with Skill Transition Models
TLDR
FIST is capable of generalizing to new tasks and substantially outperforms prior baselines in navigation experiments requiring traversing unseen parts of a large maze and 7-DoF robotic arm experiments requiring manipulating previously unseen objects in a kitchen.
Fractional quantum Hall effect in a curved space: gravitational anomaly and electromagnetic response.
TLDR
It is shown that the electromagnetic response of FQH states is related to the gravitational response (a response to curvature) and the gravitational anomaly is also seen in the structure factor and the Hall conductance in flat space.
...
1
2
3
4
...